© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 89319
    Prev
    Next
    INDEX
    Explanations

    references to navigation or pagination elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udev
    -0.07
    atsby
    -0.07
    eric
    -0.07
    ucz
    -0.07
    olas
    -0.07
    EMPLARY
    -0.07
    ismu
    -0.07
    arella
    -0.07
    cers
    -0.06
    OLA
    -0.06
    POSITIVE LOGITS
    ailing
    0.08
    iminary
    0.07
    ene
    0.07
    ail
    0.07
    istory
    0.07
    ursors
    0.07
    vy
    0.07
    inci
    0.07
    NgModule
    0.07
    anta
    0.06
    Activations Density 0.002%

    No Known Activations